Mamba-in-Computer-Vision

Mamba-in-Vision

A paper list of some recent Mamba-based CV works. If you find some ignored papers, please open issues or pull requests.

**Last updated: 2024/08/12

Mamba

• (arXiv 2023.12) Mamba: Linear-Time Sequence Modeling with Selective State Spaces, [Paper], [Code]

Survey

• (arXiv 2024.04) Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges, [Paper], [Project]
• (arXiv 2024.04) A Survey on Visual Mamba, [Paper]
• (arXiv 2024.04) State Space Model for New-Generation Network Alternative to Transformers: A Survey, [Paper], [Project]
• (arXiv 2024.05) A Survey on Vision Mamba: Models, Applications and Challenges, [Paper], [Project]
• (arXiv 2024.05) Vision Mamba: A Comprehensive Survey and Taxonomy, [Paper], [Project]

Recent Papers

Action

• (arXiv 2024.03) HARMamba: Efficient Wearable Sensor Human Activity Recognition Based on Bidirectional Selective SSM, [Paper]
• (arXiv 2024.04) Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos, [Paper]

Adversarial Attack

• (arXiv 2024.03) Understanding Robustness of Visual State Space Models for Image Classification, [Paper]

Anomaly Detection

• (arXiv 2024.04) MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection, [Paper], [Code]
• (arXiv 2024.07) ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement, [Paper], [Code]

Assessment

• (arXiv 2024.06) Q-Mamba: On First Exploration of Vision Mamba for Image Quality Assessment, [Paper], [Code]

Autonomous Driving

• (arXiv 2024.05) DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving, [Paper]

Classification (Backbone)

• (arXiv 2024.01) Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model, [Paper], [Code]
• (arXiv 2024.01) VMamba: Visual State Space Model, [Paper], [Code]
• (arXiv 2024.02) Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining, [Paper], [Code]
• (arXiv 2024.02) Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning, [Paper],[Code]
• (arXiv 2024.02) Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data, [Paper]
• (arXiv 2024.03) LocalMamba: Visual State Space Model with Windowed Selective Scan, [Paper], [Code]
• (arXiv 2024.03) EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba, [Paper], [Code]
• (arXiv 2024.03) On the low-shot transferability of [V]-Mamba, [Paper]
• (arXiv 2024.03) SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series, [Paper], [Code]
• (arXiv 2024.03) PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition, [Paper],[Code]
• (arXiv 2024.03) MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection, [Paper],[Code]
• (arXiv 2024.05) Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model, [Paper],[Code]
• (arXiv 2024.05) Scalable Visual State Space Model with Fractal Scanning, [Paper]
• (arXiv 2024.05) Mamba-R: Vision Mamba ALSO Needs Registers, [Paper]
• (arXiv 2024.05) Demystify Mamba in Vision: A Linear Attention Perspective, [Paper],[Code]
• (arXiv 2024.05) Vim-F: Visual State Space Model Benefiting from Learning in the Frequency Domain, [Paper],[Code]
• (arXiv 2024.06) Autoregressive Pretraining with Mamba in Vision, [Paper],[Code]
• (arXiv 2024.06) Towards Evaluating the Robustness of Visual State Space Models, [Paper],[Code]
• (arXiv 2024.06) MambaVision: A Hybrid Mamba-Transformer Vision Backbone, [Paper],[Code]
• (arXiv 2024.07) GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model, [Paper],[Code]

Compression

• (arXiv 2024.05) MambaVC: Learned Visual Compression with Selective State Spaces, [Paper]

Crowd Counting

• (arXiv 2024.05) VMambaCC: A Visual State Space Model for Crowd Counting, [Paper]

Deblurring

• (arXiv 2024.03) Aggregating Local and Global Features via Selective State Spaces Model for Efficient Image Deblurring, [Paper],[Code]
• (arXiv 2024.05) Efficient Visual State Space Model for Image Deblurring, [Paper]

Dehazing

• (arXiv 2024.02) U-shaped Vision Mamba for Single Image Dehazing, [Paper],[Code]
• (arXiv 2024.05) RSDehamba: Lightweight Vision Mamba for Remote Sensing Satellite Image Dehazing, [Paper]

Depth

• (arXiv 2024.06) MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimation, [Paper],[Code]

Deraining

• (arXiv 2024.04) FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining, [Paper]
• (arXiv 2024.05) Image Deraining with Frequency-Enhanced State Space Model, [Paper]
• (arXiv 2024.08) RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining, [Paper],[Code]

Detection

• (arXiv 2024.03) MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection, [Paper],[Code]
• (arXiv 2024.04) Fusion-Mamba for Cross-modality Object Detection, [Paper]
• (arXiv 2024.04) CFMW: Cross-modality Fusion Mamba for Multispectral Object Detection under Adverse Weather Conditions, [Paper],[Code]
• (arXiv 2024.05) SOAR: Advancements in Small Body Object Detection for Aerial Imagery Using State Space Models and Programmable Gradients, [Paper],[Code]
• (arXiv 2024.06) Mamba YOLO: SSMs-Based YOLO For Object Detection, [Paper],[Code]
• (arXiv 2024.08) MonoMM: A Multi-scale Mamba-Enhanced Network for Real-time Monocular 3D Object Detection, [Paper]
• (arXiv 2024.08) MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection, [Paper],[Code]

Diffusion

• (arXiv 2024.03) ZigMa: Zigzag Mamba Diffusion Model, [Paper],[Code]
• (arXiv 2024.05) DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis, [Paper],[Code]
• (arXiv 2024.05) Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation, [Paper]
• (arXiv 2024.06) Dimba: Transformer-Mamba Diffusion Models, [Paper],[Code]
• (arXiv 2024.08) LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba, [Paper]

Domain

• (arXiv 2024.04) DGMamba: Domain Generalization via Generalized State Space Model, [Paper],[Code]

Enhancement

• (arXiv 2024.04) MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 FLOPs, [Paper],[Code]
• (arXiv 2024.05) Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement, [Paper],[Code]
• (arXiv 2024.05) WaterMamba: Visual State Space Model for Underwater Image Enhancement, [Paper]
• (arXiv 2024.05) MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space, [Paper]
• (arXiv 2024.06) LLEMamba: Low-Light Enhancement via Relighting-Guided Mamba with Deep Unfolding Network, [Paper]
• (arXiv 2024.06) PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement, [Paper],[Code]
• (arXiv 2024.07) RESVMUNetX: A Low-Light Enhancement Network Based on VMamba, [Paper]
• (arXiv 2024.08) Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement, [Paper],[Code]

Event Cameras

• (arXiv 2024.02) State Space Models for Event Cameras, [Paper]
• (arXiv 2024.04) MambaPupil: Bidirectional Selective Recurrent model for Event-based Eye tracking, [Paper]

Face

• (arXiv 2024.05) FER-YOLO-Mamba: Facial Expression Detection and Classification Based on Selective State Space, [Paper],[Code]